LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
hub
a is b" fail to learn
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
DiscoLoop adds a decoded token-embedding channel to looped transformers, fixing a representation mismatch that limited implicit multi-hop reasoning and improving OOD generalization.
ArBG replaces flow-based methods with autoregressive models for Boltzmann sampling, showing gains on peptide benchmarks and a 132M-parameter model Robin cutting zero-shot energy error by over 60% on 8-residue systems.
Introduces TTS, a dependent type theory replacing global canonical composition with regime-indexed indiscernibility and constructive apartness, proving conservativity, provenance, no-fork-from-empty, and persistence of forks under refinement.
LLM self-explanations for entity resolution are unstable and weakly faithful to causal evidence, but a hybrid framework using them as priors matches post-hoc quality at up to 10x lower cost.
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
Compositionality emerges in neural networks only in a narrow depth-connectivity regime, with gradient descent converging to fractured solutions outside it.
Frontier LLMs exhibit moral deliberative sycophancy by shifting their moral reasoning and justifications up to 6.5% on average toward a user's stated preferred view in simulated deliberations.
MARD-7B outperforms baselines and GPT-4o on novel drug pairs for mechanism-level DDI prediction via a new distillation pipeline with verifiable process rewards and releases all resources.
Decan (D_Ca_n = C × a_n) measures text diversity as progressive conditional surprise from base LM log-probabilities, scoring 0.846 OCA on McDiv benchmark and detecting monotonic diversity drop across base→SFT→DPO→RLVR stages.
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
Trace mutations are a class of context failures in LLM conversations consisting of utterance effacement and genitive dissociation that distort the shared record while resisting ordinary repair.
Bidirectional objectives mitigate reversal by requiring explicit source-as-target signals and storing directions as distinct representations instead of inducing latent generalization.
A mask-and-reconstruct fine-tuning objective lets autoregressive LLMs inject new knowledge without paraphrases and largely removes the reversal curse.
ArgLLMs build argumentation frameworks from LLMs to support explainable and contestable formal reasoning for claim verification.
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
Dynamic-dLLM achieves over 3x average inference speedup on dLLMs like LLaDA-8B via adaptive cache budgets and decoding thresholds while preserving benchmark performance.
MeMo encodes new knowledge into a separate memory model that integrates with frozen LLMs, showing strong performance on QA benchmarks while avoiding catastrophic forgetting and working without access to model weights.
Absurd World automatically converts real-world problems into absurd yet logically coherent scenarios to test whether LLMs can reason without depending on familiar patterns.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.
citing papers explorer
-
Large Language Diffusion Models
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
-
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
DiscoLoop adds a decoded token-embedding channel to looped transformers, fixing a representation mismatch that limited implicit multi-hop reasoning and improving OOD generalization.
-
Autoregressive Boltzmann Generators
ArBG replaces flow-based methods with autoregressive models for Boltzmann sampling, showing gains on peptide benchmarks and a 132M-parameter model Robin cutting zero-shot energy error by over 60% on 8-residue systems.
-
A Type Theory of Sense: Witnessed Choice in Stratified Semantic Spaces
Introduces TTS, a dependent type theory replacing global canonical composition with regime-indexed indiscernibility and constructive apartness, proving conservativity, provenance, no-fork-from-empty, and persistence of forks under refinement.
-
Can we trust LLM Self-Explanations for Entity Resolution?
LLM self-explanations for entity resolution are unstable and weakly faithful to causal evidence, but a hybrid framework using them as priors matches post-hoc quality at up to 10x lower cost.
-
Adaptive Order Policies for Masked Diffusion
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
-
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
-
Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds
Compositionality emerges in neural networks only in a narrow depth-connectivity regime, with gradient descent converging to fractured solutions outside it.
-
Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs
Frontier LLMs exhibit moral deliberative sycophancy by shifting their moral reasoning and justifications up to 6.5% on average toward a user's stated preferred view in simulated deliberations.
-
MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction
MARD-7B outperforms baselines and GPT-4o on novel drug pairs for mechanism-level DDI prediction via a new distillation pipeline with verifiable process rewards and releases all resources.
-
"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional Surprise
Decan (D_Ca_n = C × a_n) measures text diversity as progressive conditional surprise from base LM log-probabilities, scoring 0.846 OCA on McDiv benchmark and detecting monotonic diversity drop across base→SFT→DPO→RLVR stages.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
Trace Mutation in Human-LLM Dialogue: The Transcript as Forensic and Mitigation Surface
Trace mutations are a class of context failures in LLM conversations consisting of utterance effacement and genitive dissociation that distort the shared record while resisting ordinary repair.
-
The Illusion of Latent Generalization: Bi-directionality and the Reversal Curse
Bidirectional objectives mitigate reversal by requiring explicit source-as-target signals and storing directions as distinct representations instead of inducing latent generalization.
-
Diffusion-Inspired Masked Fine-Tuning for Knowledge Injection in Autoregressive LLMs
A mask-and-reconstruct fine-tuning objective lets autoregressive LLMs inject new knowledge without paraphrases and largely removes the reversal curse.
-
Argumentative Large Language Models for Explainable and Contestable Claim Verification
ArgLLMs build argumentation frameworks from LLMs to support explainable and contestable formal reasoning for claim verification.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
Dynamic-dLLM achieves over 3x average inference speedup on dLLMs like LLaDA-8B via adaptive cache budgets and decoding thresholds while preserving benchmark performance.
-
MeMo: Memory as a Model
MeMo encodes new knowledge into a separate memory model that integrates with frozen LLMs, showing strong performance on QA benchmarks while avoiding catastrophic forgetting and working without access to model weights.
-
Absurd World: A Simple Yet Powerful Method to Absurdify the Real-world for Probing LLM Reasoning Capabilities
Absurd World automatically converts real-world problems into absurd yet logically coherent scenarios to test whether LLMs can reason without depending on familiar patterns.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Measuring AI Reasoning: A Guide for Researchers
Reasoning in language models should be measured by the faithfulness and validity of their multi-step search processes and intermediate traces, not final-answer accuracy.